© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31380
    Prev
    Next
    INDEX
    Explanations

    close relationships such as friends, associates, and supporters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.16
    0.7%
    673
    +0.11
    0.5%
    323
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.16
    0.09
    323
    +0.11
    0.10
    247
    +0.11
    0.07
    Negative Logits
     probabilities
    -0.68
    onew
    -0.67
    aqu
    -0.65
    utterstock
    -0.65
     feasibility
    -0.64
     futures
    -0.64
    missing
    -0.62
    ammers
    -0.62
    Auth
    -0.60
     equival
    -0.60
    POSITIVE LOGITS
    lier
    0.90
     collaborators
    0.84
     collaborator
    0.83
    76561
    0.80
     confid
    0.73
     ally
    0.71
     mentor
    0.68
     dearly
    0.67
    liness
    0.67
     Neighbor
    0.67
    Activations Density 11.582%

    No Known Activations